Skip to content
View froggychips's full-sized avatar
🌴
Be free, be frog 🐸
🌴
Be free, be frog 🐸

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Block or report froggychips

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
froggychips/README.md

froggychips

Bangkok · working at the edges of:

  • Apple Silicon + on-device LLMs — Froggy: MLX + Vision OCR on 8 GB Macs.
  • SRE / agentic incident response — sre-ai-copilot.
  • Claude Code tooling — mcp-skills-vault.
  • Browser AI for X / Twitter — TweAI: Chrome extension, BYOK, no backend.

Telegram: @froggychips In Frog We Trust🐸

Pinned Loading

  1. Froggy Froggy Public

    On-device LLM + screen OCR for macOS. Native Swift 6, MLX, ScreenCaptureKit. Optimized for low-RAM Apple Silicon (8 GB).

    Swift

  2. mcp-skills-vault mcp-skills-vault Public

    Claude Code skills for discovering, scoring, and installing MCP (Model Context Protocol) servers — registry-first with a seeded 30-tool database and a token-safe install path.

    JavaScript

  3. sre-ai-copilot sre-ai-copilot Public

    AI-driven incident response copilot for Kubernetes. AlertManager webhook → agent pipeline (analyzer/hypothesis/critic/fix/risk) → human approval. FastAPI + Celery + LLM, k8s namespace guardrails.

    Python